Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add KirKruglov/claude-project-manager --skill generate-risk-registergit clone --depth 1 https://github.com/KirKruglov/claude-project-managerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kirkruglov/claude-project-manager/generate-risk-register)<a href="https://agentmods.dev/skills/kirkruglov/claude-project-manager/generate-risk-register"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-project-manager/generate-risk-register/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kirkruglov/claude-project-manager/generate-risk-register"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-project-manager/generate-risk-register.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.03544 |
| Opus 5 | $0.00054 | $0.01772 |
| Sonnet 5 | $0.00022 | $0.00709 |
| Haiku 4.5 | $0.00011 | $0.00354 |
Grade A, and why
generate-risk-register scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
98% identical to generate-risk-register — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
generate-risk-register
Triggers
Russian: «сформируй реестр рисков», «подготовь risk register», «обнови реестр рисков» English: "generate risk register", "create risk register", "update risk register"
Language Detection
Determine the language of the user's request:
- If the request is in Russian → use templates with
-rusuffix - Otherwise → use templates with
-ensuffix
All output (headings, labels, comments, instructions) must match the detected language.
1. Input Data
Initial mode (phase 1)
| Data | Required | Source | Notes |
|---|---|---|---|
| Project charter (project-charter.md) | yes | knowledge | Primary context: goal, scope, timeline, budget, constraints, assumptions |
| Project type / industry | no | chat or knowledge | Used to select industry-typical risks. If not specified — agent infers from charter |
| Additional context | no | chat | User comments on specific risks |
Detailed mode (phase 2)
| Data | Required | Source | Notes |
|---|---|---|---|
| Project charter (project-charter.md) | yes | knowledge | Project context |
| Project plan (project-plan.md) | yes | knowledge | WBS, timeline, resources, dependencies — source of new risks |
| Risk register v1 (risk-register.md) | yes | knowledge | Output of initial mode — base for update |
| Additional context | no | chat | New risks identified by the user |
If required data is missing — request using this template:
To generate the risk register, the following is required:
— Initial mode: approved project charter (project-charter.md).
— Detailed mode: charter + project plan (project-plan.md) + current risk register (risk-register.md).
Available data: [list what is available].
Missing: [be specific].
2. Execution Algorithm
- Determine mode. If the user has not specified — infer from context: project plan present → detailed, charter only → initial. If ambiguous — ask.
- Verify input data. Minimum data for the selected mode is present → step 3. Missing → request using the template from §1. Do NOT generate a placeholder or sample register.
- Read the template
risk-register-ru.mdorrisk-register-en.mdfrom project knowledge (based on detected language). - Identify risks.
- Initial: Analyze the charter from scratch — goal, scope (included and excluded), timeline, budget, constraints, assumptions, team composition. For each charter section evaluate: what could go wrong? Use categories from the reference table (§3). Recommended count: 5–10 risks. Do not automatically copy the top-3 risks from the charter — perform an independent analysis (charter risks may enter the register if confirmed by analysis).
- Detailed: Use register v1 as the base. Analyze the project plan: WBS (which work packages are highest risk?), critical path, dependencies, resource constraints. Add new risks. Update assessments of existing risks (probability/impact may have changed). For each risk — link to WP-xxx from the plan, assign a specific owner from project-plan. Specify actions concretely.
- Assess each risk using the scale from the reference table (§3): category, probability (H/M/L), impact (H/M/L), level, strategy (Avoid/Mitigate/Transfer/Accept). Level is calculated strictly by the table below — not by intuition or proximity to adjacent cells:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 277 lines · 108 tokens per session scan A 86a67211bba8
generate-risk-register is a skill published in the GitHub repository KirKruglov/claude-project-manager (6 stars, last pushed 4mo ago), licensed MIT. It adds 108 tokens to every session and 3,544 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to generate-risk-register, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
litigation-workflow
Civil litigation workflow expertise — case management, deposition prep, evidence chain, and Federal Rules of Evidence.
construction-management
Estimating, scheduling, building codes, safety protocols, permitting, and project controls.
stakeholder-communication
Owner reports, subcontractor coordination, RFI responses, and meeting documentation.
run-team-retrospective
Use when a team needs to reflect on a completed period, project, or significant event — to extract what worked, what didn't, and what specific changes to make before the next cycle, rather than repeating the same patterns.
project-manager
This skill has been upgraded with agentic AI capabilities, OKR/KPI integration patterns, and async-first workflows based on 2026 PM best practices research.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.